Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix SAC + LSTM Barracuda inference #2698

Merged
merged 1 commit into from
Oct 9, 2019
Merged

Fix SAC + LSTM Barracuda inference #2698

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions ml-agents/mlagents/trainers/sac/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -556,10 +556,13 @@ def create_memory_ins(self, m_size):
)
# We assume m_size is divisible by 4
# Create the non-Policy inputs
# Use a default placeholder here so nothing has to be provided during
# Barracuda inference. Note that the default value is just the tiled input
# for the policy, which is thrown away.
three_fourths_m_size = m_size * 3 // 4
self.other_memory_in = tf.placeholder(
self.other_memory_in = tf.placeholder_with_default(
input=tf.tile(self.inference_memory_in, [1, 3]),
shape=[None, three_fourths_m_size],
dtype=tf.float32,
name="other_recurrent_in",
)

Expand Down